© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15076
    Prev
    Next
    INDEX
    Explanations

    shapes and geometric patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anc
    -0.11
     hormones
    -0.10
     electricity
    -0.10
     plumbing
    -0.10
     food
    -0.10
     skincare
    -0.10
     vegetables
    -0.10
     prostitu
    -0.10
     physical
    -0.09
     minerals
    -0.09
    POSITIVE LOGITS
     spiral
    0.16
     circular
    0.16
     double
    0.16
     Double
    0.15
     triangular
    0.15
    Double
    0.15
     rectangular
    0.15
     Circular
    0.15
     diagonal
    0.15
     zig
    0.15
    Activations Density 3.970%

    No Known Activations